Concurrent Speech Signal Separation Based on Frequency Domain Binaural Model

@inproceedings{Chisaki2003ConcurrentSS,
  title={Concurrent Speech Signal Separation Based on Frequency Domain Binaural Model},
  author={Yoshifumi Chisaki and Takashi Nakanishi and Hidetoshi Nakashima and Tsuyoshi Usagawa},
  year={2003}
}
We can communicate with others in a noisy environment. This phenomenon is known as a “Cocktail Party Effect,” and is one of the most important binaural functions. In our previous study, frequency domain binaural model (FDBM) based on interaural phase difference (IPD) and interaural level difference (ILD) was proposed, and its performance as the front-end of the speech recognition system was confirmed. However, the model estimates direction of arrival (DOA) of the sound sources only in azimuth… CONTINUE READING